gmail-opportunity-progress
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from Gmail messages to update a database.
- Ingestion points: The skill searches and reads body content, subjects, and sender information from Gmail threads (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or discard natural language instructions that might be embedded within the emails it reads.
- Capability inventory: The skill utilizes Gmail and Notion MCP/API tools to read messages and write status updates/notes to a tracker.
- Sanitization: While the skill instructs the agent to summarize operational facts rather than pasting full email bodies, this does not prevent the underlying LLM from potentially following instructions found within the email content during the classification phase.
Audit Metadata